aboutsummaryrefslogtreecommitdiffstats
path: root/libibex/words.c
blob: 1a5a4d568059f83ee7834b5383b96d96d7ebca6e (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
/*
 * Copyright (C) 2000 Helix Code, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Library General Public License
 * as published by the Free Software Foundation; either version 2 of
 * the License, or (at your option) any later version.
 * 
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Library General Public License for more details.
 *
 * You should have received a copy of the GNU Library General Public
 * License along with the Gnome Library; see the file COPYING.LIB.  If not,
 * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 */

/* words.c: low-level indexing ops */

#include <ctype.h>
#include <errno.h>
#include <string.h>

#include <unicode.h>

#include "ibex_internal.h"

static signed char utf8_trans[] = {
    'A', 'A', 'A', 'A', 'A', 'A', -1, 'C', 'E', 'E', 'E', 'E', 'I', 'I',
    'I', 'I', -2, 'N', 'O', 'O', 'O', 'O', 'O', '*', 'O', 'U', 'U', 'U',
    'U', 'Y', -3, -4, 'a', 'a', 'a', 'a', 'a', 'a', -5, 'c', 'e', 'e',
    'e', 'e', 'i', 'i', 'i', 'i', -6, 'n', 'o', 'o', 'o', 'o', 'o', '/',
    'o', 'u', 'u', 'u', 'u', 'y', -7, 'y', 'A', 'a', 'A', 'a', 'A', 'a',
    'C', 'c', 'C', 'c', 'C', 'c', 'C', 'c', 'D', 'd', 'D', 'd', 'E', 'e',
    'E', 'e', 'E', 'e', 'E', 'e', 'E', 'e', 'G', 'g', 'G', 'g', 'G', 'g',
    'G', 'g', 'H', 'h', 'H', 'h', 'I', 'i', 'I', 'i', 'I', 'i', 'I', 'i',
    'I', 'i', -8, -9, 'J', 'j', 'K', 'k', 'k', 'L', 'l', 'L', 'l', 'L',
    'l', 'L', 'l', 'L', 'l', 'N', 'n', 'N', 'n', 'N', 'n', 'n', -10, -11,
    'O', 'o', 'O', 'o', 'O', 'o', -12, -13, 'R', 'r', 'R', 'r', 'R', 'r',
    'S', 'r', 'S', 's', 'S', 's', 'S', 's', 'T', 't', 'T', 't', 'T', 't',
    'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'W', 'w',
    'Y', 'y', 'Y', 'Z', 'z', 'Z', 'z', 'Z', 'z', 's'
};

static char *utf8_long_trans[] = {
    "AE", "TH", "TH", "ss", "ae", "th", "th", "IJ", "ij",
    "NG", "ng", "OE", "oe"
};

/* This is a bit weird. It takes pointers to the start and end (actually
 * just past the end) of a UTF-8-encoded word, and a buffer at least 1
 * byte longer than the length of the word. It copies the word into the
 * buffer in all lowercase without accents, and splits up ligatures.
 * (Since any ligature would be a multi-byte character in UTF-8, splitting
 * them into two US-ASCII characters won't overrun the buffer.)
 *
 * It is not safe to call this routine with bad UTF-8.
 */
static void
normalize_word (char *start, char *end, char *buf)
{
    unsigned char *s, *d;
    unicode_char_t uc;

    s = (unsigned char *)start;
    d = (unsigned char *)buf;
    while (s < (unsigned char *)end) {
        if (*s < 0x80) {
            /* US-ASCII character: copy unless it's
             * an apostrophe.
             */
            if (*s != '\'')
                *d++ = tolower (*s);
            s++;
        } else {
            char *next = unicode_get_utf8 (s, &uc);
            if (uc >= 0xc0 && uc < 0xc0 + sizeof (utf8_trans)) {
                signed char ch = utf8_trans[uc - 0xc0];
                if (ch > 0)
                    *d++ = tolower (ch);
                else {
                    *d++ = tolower (utf8_long_trans[-ch - 1][0]);
                    *d++ = tolower (utf8_long_trans[-ch - 1][1]);
                }
                s = next;
            } else {
                while (s < (unsigned char *)next)
                    *d++ = *s++;
            }
        }
    }
    *d = '\0';
}

enum { IBEX_ALPHA, IBEX_NONALPHA, IBEX_INVALID, IBEX_INCOMPLETE };

/* This incorporates parts of libunicode, because there's no way to
 * force libunicode to not read past a certain point.
 */
static int
utf8_category (char *sp, char **snp, char *send)
{
    unsigned char *p = (unsigned char *)sp, **np = (unsigned char **)snp;
    unsigned char *end = (unsigned char *)send;

    if (isascii (*p)) {
        *np = p + 1;
        if (isalpha (*p) || *p == '\'')
            return IBEX_ALPHA;
        return IBEX_NONALPHA;
    } else {
        unicode_char_t uc;
        int more;

        if ((*p & 0xe0) == 0xc0) {
            more = 1;
            uc = *p & 0x1f;
        } else if ((*p & 0xf0) == 0xe0) {
            more = 2;
            uc = *p & 0x0f;
        } else if ((*p & 0xf8) == 0xf0) {
            more = 3;
            uc = *p & 0x07;
        } else if ((*p & 0xfc) == 0xf8) {
            more = 4;
            uc = *p & 0x03;
        } else if ((*p & 0xfe) == 0xfc) {
            more = 5;
            uc = *p & 0x01;
        } else
            return IBEX_INVALID;

        if (p + more > end)
            return IBEX_INCOMPLETE;

        while (more--) {
            if ((*++p & 0xc0) != 0x80)
                return IBEX_INVALID;
            uc <<= 6;
            uc |= *p & 0x3f;
        }

        *np = p + 1;
        if (unicode_isalpha (uc))
            return IBEX_ALPHA;
        else
            return IBEX_NONALPHA;
    }
}

static ibex_file *
get_ibex_file (ibex *ib, char *name)
{
    ibex_file *ibf;

    ibf = g_tree_lookup (ib->files, name);
    if (!ibf) {
        ibf = g_malloc (sizeof (ibex_file));
        ibf->name = strdup (name);
        ibf->index = 0;
        g_tree_insert (ib->files, ibf->name, ibf);
        ib->dirty = TRUE;
    }
    return ibf;
}

static void
ref_word (ibex *ib, ibex_file *ibf, char *word)
{
    GPtrArray *refs;

    refs = g_hash_table_lookup (ib->words, word);
    if (!refs) {
        refs = g_ptr_array_new ();
        g_hash_table_insert (ib->words, g_strdup (word), refs);
        g_ptr_array_add (refs, ibf);
        ib->dirty = TRUE;
    } else if (g_ptr_array_index (refs, refs->len - 1) != ibf) {
        g_ptr_array_add (refs, ibf);
        ib->dirty = TRUE;
    }
}

int
ibex_index_buffer (ibex *ib, char *name, char *buffer,
           size_t len, size_t *unread)
{
    char *p, *q, *nq, *end, *word;
    ibex_file *ibf = get_ibex_file (ib, name);
    int wordsiz, cat;

    end = buffer + len;
    wordsiz = 20;
    word = g_malloc (wordsiz);

    p = buffer;
    while (p < end) {
        while (p < end) {
            cat = utf8_category (p, &q, end);
            if (cat != IBEX_NONALPHA)
                break;
            p = q;
        }
        if (p == end) {
            g_free (word);
            return 0;
        } else if (cat == IBEX_INVALID) {
            errno = EINVAL;
            g_free (word);
            return -1;
        } else if (cat == IBEX_INCOMPLETE)
            q = end;

        while (q < end) {
            cat = utf8_category (q, &nq, end);
            if (cat != IBEX_ALPHA)
                break;
            q = nq;
        }
        if (cat == IBEX_INVALID ||
            (cat == IBEX_INCOMPLETE && !unread)) {
            errno = EINVAL;
            g_free (word);
            return -1;
        } else if (cat == IBEX_INCOMPLETE || (q == end && unread)) {
            *unread = end - p;
            g_free (word);
            return 0;
        }

        if (wordsiz < q - p + 1) {
            wordsiz = q - p + 1;
            word = g_realloc (word, wordsiz);
        }
        normalize_word (p, q, word);
        ref_word (ib, ibf, word);
        p = q;
    }

    if (unread)
        *unread = 0;
    g_free (word);
    return 0;
}